A must read for anyone interested in embodied cognition (I assume that that computationalists know this already)https://twitter.com/tyrell_turing/status/1043153851711279105 …
-
-
*Conceptually simple. Also NOR is possible too.
-
Not sure what you mean
@asehelene. Do you mean people tend to associate "TM" with desktop computer and think of computational theory of mind as 'metaphor'? -
Yes, very much so. Hence ”hardwired” etc. but my sense also, teaching masters, is they have zero background on algorithms, standard logic, etc. going thru the cog revolution including Turing is new to them.
-
Coming from UG psych?
-
Yes- internationally. I did cog psy in early 90 and had to learn c ++ Lisp and fid neural nets, some non linesr dynamics and math and logic in addition. Hard to find common ground for teaching theoretical aspects.
-
I always thought psy needed more formal things (I purdued it voluntarily) but it hasn’t happened. Very smart students, but formsl aspects still not huge part.
-
For a brief moment, I thought you had verbed Purdue University. :-)
- 3 more replies
New conversation -
-
-
Mmmm, not quite. You need to show it can implement any arbitrary set of NAND operations. Not so simple, but something that multilayer and RNNs can do.
-
I thought recurrent connections necessary to get the infinite memory (otherwise not finite number of layers?).
-
No, just infinitely wide, potentially.
-
OK, same issue.
-
Recursion seems to me infinitely more plausible than infinite sized networks.
-
Yes, agreed.
-
"You need to show it can implement any arbitrary set of NAND operations." For the NN: yes. For a programming language, that's already a given.
-
So yeah, I should have been clearer.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
=
):